cognitive-core 0.2.4 → 0.3.1

package/gaps.md

@@ -1,204 +0,0 @@
-# Team-Aware Trajectory Learning: Implementation Gap Analysis
-
-> Generated from comparison of RESEARCH-team-trajectory-learning.md, PROPOSAL-team-aware-learning.md,
-> DESIGN-team-extraction-pipeline.md against the current implementation.
-
-## Summary
-
-| Severity | Total | Fixed | Deferred |
-|----------|-------|-------|----------|
-| HIGH     | 3     | 3     | 0        |
-| MEDIUM   | 10    | 4     | 6        |
-| LOW      | 17    | 10    | 7        |
-
----
-
-## HIGH Priority
-
-### Gap 1: Graph-based vs event-stream TeamTrajectory
-- **Source:** DESIGN doc specifies `members: MemberTrajectory[]` (full `Trajectory` objects per agent) + `interactions: AgentInteraction[]`. Implementation uses flat `events: TeamEvent[]` + `interactionGraph: InteractionEdge[]` (PROPOSAL model).
-- **Impact:** Loses per-agent step-level detail needed for compression, critical step identification, and fine-grained credit attribution.
-- **Status:** FIXED
-- **Fix:** Additive graph migration. Added `MemberTrajectory`, `AgentInteraction`, `GraphStructuralMetrics` types. Added optional graph fields (`members`, `interactions`, `graphMetrics`, `expectedPatterns`) to `TeamTrajectory`. Updated `buildTeamTrajectory()` to populate both graph and flat data. Updated ingester with graph-aware scoring (content-based step scoring, downstream success analysis). Migrated all consumers (pipeline, meta-learner, extraction, analysis template) to prefer graph data with flat fallback. 16 new tests added.
-
-### Gap 2: `TeamTrajectoryInput` entry point missing
-- **Source:** DESIGN specifies `TeamTrajectoryInput` with `memberTrajectories: { agentId, role, trajectory: Trajectory }[]` as the ingest entry point that gets converted to `TeamTrajectory`.
-- **Impact:** No way to ingest raw individual trajectories and automatically build the team trajectory graph.
-- **Status:** FIXED
-- **Fix:** Add `TeamTrajectoryInput` type and `buildTeamTrajectory()` conversion function.
-
-### Gap 3: `InteractionTag` runtime capture missing
-- **Source:** DESIGN specifies `InteractionTag` interface (`interactionId`, `interactionType`, `counterpartAgentId`, `stepRole`) as step metadata for automatic interaction graph construction.
-- **Impact:** No automatic way to tag agent interactions during execution. Users must manually construct `interactionGraph`.
-- **Status:** FIXED
-- **Fix:** Add `InteractionTag` and `InteractionType` types. Add `buildInteractionGraph()` utility that extracts edges from tagged steps.
-
----
-
-## MEDIUM Priority
-
-### Gap 4: Trajectory compression not implemented
-- **Source:** DESIGN Phase 2 specifies per-agent trajectory compression: fold internal steps, strip verbose output, preserve interaction boundaries, target ~10x reduction.
-- **Impact:** Analysis operates on raw data, reducing quality and increasing cost for agentic analysis.
-- **Status:** DEFERRED - Requires graph-based TeamTrajectory (Gap 1). The ingester scores critical steps/interactions for prioritization, which partially addresses this.
-- **Fix:** N/A (depends on Gap 1)
-
-### Gap 5: Analysis output schema missing fields
-- **Source:** DESIGN specifies richer output types than implemented.
-- **Impact:** Lost detail in analysis results.
-- **Status:** FIXED
-- **Fix:** Add `stepAttributions` to `AgentCredit`, `type`/`contentQuality` to `InteractionCredit`, `patternComparison`/`emergentCoordination` to `CoordinationAssessment`, `interactionAssessment`/`evidence` to `RoleLessonEntry`.
-
-### Gap 6: `spawnTeamMember()` not implemented
-- **Source:** DESIGN specifies `Atlas.spawnTeamMember(config)` that injects both task playbooks and role playbooks into spawned team member agents.
-- **Impact:** No integrated way to spawn agents with full knowledge injection.
-- **Status:** DEFERRED - Runtime integration concern. Requires AgentManager + SkillLibrary coordination. The `formatRoleGuidance()` method provides the role playbook content for manual injection.
-- **Fix:** N/A (runtime integration)
-
-### Gap 7: `ExpectedInteractionPattern` type missing
-- **Source:** DESIGN specifies `ExpectedInteractionPattern` for comparing expected vs actual coordination patterns, and `AgentInteraction.wasExpected` flag.
-- **Impact:** Cannot compare observed coordination against expected patterns from team.yaml.
-- **Status:** FIXED
-- **Fix:** Add `ExpectedInteractionPattern` type to team-trajectory.ts.
-
-### Gap 8: Analysis agent meta-learning loop missing
-- **Source:** DESIGN specifies capturing the analysis agent's own trajectory and feeding it through the individual `LearningPipeline` with domain `"team-analysis"`.
-- **Impact:** System doesn't learn to be better at team analysis over time.
-- **Status:** DEFERRED - Requires AgentManager integration to capture analysis agent trajectories. The template infrastructure supports this but the pipeline doesn't wire it.
-- **Fix:** N/A (runtime integration)
-
-### Gap 9: Knowledge injection for analysis agents empty
-- **Source:** DESIGN specifies `getAnalysisKnowledge()` querying team playbooks, similar experiences, and individual memory. Templates return empty `getSkills()`/`getResources()`.
-- **Impact:** Analysis agents operate without prior knowledge context.
-- **Status:** DEFERRED - Templates are stateless and don't have access to memory at definition time. Would need a factory pattern or dependency injection to resolve.
-- **Fix:** N/A (architectural pattern needed)
-
-### Gap 10: Playbook updates/refinements not applied
-- **Source:** Batch extraction produces `TeamPlaybookUpdate`/`RolePlaybookUpdate` with refinement context/additions. Pipeline counts them but discards them (no `updatePlaybook()` method).
-- **Impact:** Existing playbooks never get refined from new experiences.
-- **Status:** FIXED
-- **Fix:** Add `updateTeamPlaybook()`/`updateRolePlaybook()` methods to `TeamExperienceMemory` and wire into pipeline's batch learning.
-
-### Gap 11: Cross-pollination references never populated
-- **Source:** DESIGN specifies `RolePlaybookReference` on TeamPlaybook and `RelatedTaskPlaybook` on RolePlaybook. Types exist but heuristic extraction never populates them.
-- **Impact:** No cross-linking between team playbooks and role/task playbooks.
-- **Status:** FIXED
-- **Fix:** Add cross-pollination logic to heuristic extraction.
-
-### Gap 12: Meta-learner fragile topology extraction
-- **Source:** `TeamMetaLearner.generateReflection()` extracts topology assessment from `trajectory.topologyType` but `analyzeTopologyEffectiveness()` uses regex on `obs.compositionEffectiveness.topologyAssessment` (a string like 'effective'/'neutral'/'hindering') to match topologies.
-- **Impact:** Topology analysis is unreliable and may produce incorrect meta-strategies.
-- **Status:** FIXED
-- **Fix:** Use the `teamTrajectoryId` to look up the actual trajectory's `topologyType` from meta-observations, or store topology directly on the observation.
-
-### Gap 13: Vector embeddings for team data missing
-- **Source:** DESIGN specifies extending `vectors.db` with team embeddings for semantic search. `TeamExperienceMemory` uses `JsonStore` with text-matching heuristics.
-- **Impact:** Team playbook/experience search relies on keyword matching instead of semantic similarity.
-- **Status:** DEFERRED - Requires EmbeddingManager integration. The current text-matching approach works for small datasets. Add as future enhancement when team data volume grows.
-- **Fix:** N/A (infrastructure enhancement)
-
----
-
-## LOW Priority
-
-### Gap 14: `metricsWeight` config field missing
-- **Source:** PROPOSAL specifies `metricsWeight: z.number().min(0).max(1).default(0.3)` in `TeamLearningConfigSchema`.
-- **Impact:** No way to tune how much structural metrics influence analysis.
-- **Status:** FIXED
-- **Fix:** Add field to `TeamLearningConfigSchema`.
-
-### Gap 15: `CompressionConfig` not in `TeamLearningConfig`
-- **Source:** DESIGN specifies `compression: CompressionConfig` as a nested config field with 7 parameters.
-- **Impact:** Compression parameters not configurable through main config.
-- **Status:** FIXED
-- **Fix:** Add `CompressionConfig` schema to `TeamLearningConfigSchema`.
-
-### Gap 16: `InteractionType` union type not defined
-- **Source:** DESIGN specifies `InteractionType = 'delegation' | 'result_return' | 'message' | 'signal' | 'spawn' | 'escalation'` as a distinct type from `TeamEventType`.
-- **Impact:** `RoleInteractionGuidance.interactionType` uses `string` instead of a constrained union.
-- **Status:** FIXED (combined with Gap 3)
-- **Fix:** Add `InteractionType` to team-trajectory.ts and use in RoleInteractionGuidance.
-
-### Gap 17: `TeamPlaybook.complexity` missing 'epic'
-- **Source:** `TeamPlaybook.complexity` is `'simple' | 'moderate' | 'complex'` but `TeamPlaybookApplicability.complexityLevels` includes `'epic'`. Inconsistency.
-- **Impact:** Cannot create team playbooks tagged as epic complexity.
-- **Status:** FIXED
-- **Fix:** Add `'epic'` to `TeamPlaybook.complexity` union.
-
-### Gap 18: `AnalysisWorkspace` type not formalized
-- **Source:** DESIGN specifies `AnalysisWorkspace` interface with `path`, `teamTrajectory`, `compressionStats`, `criticalMoments`.
-- **Impact:** No formal type for the workspace state between ingestion and analysis.
-- **Status:** DEFERRED - The `IngestionResult` type serves this purpose. Adding a separate type would be redundant.
-- **Fix:** N/A
-
-### Gap 19: `TeamAnalysisCollector` not a separate class
-- **Source:** DESIGN specifies `TeamAnalysisCollector` as a distinct class for collecting analysis agent output.
-- **Impact:** Collection logic is embedded in the pipeline, reducing modularity.
-- **Status:** DEFERRED - Current approach works. Separate collector class would add complexity without clear benefit at current scale.
-- **Fix:** N/A
-
-### Gap 20: Assessment workspace filesystem layout differs
-- **Source:** DESIGN specifies specific `input/`/`workspace/`/`output/` directory structure. Templates use `WorkspaceHandle` abstraction.
-- **Impact:** Minor - templates use equivalent but different abstraction.
-- **Status:** DEFERRED - WorkspaceHandle provides the same capabilities through a cleaner API.
-- **Fix:** N/A
-
-### Gap 21: `RoleLessonEntry` missing detailed fields
-- **Source:** DESIGN specifies `interactionAssessment: { withRole, interactionType, quality, observation, recommendation }[]` and `evidence: { stepIndex, description }[]`.
-- **Impact:** Role lessons lack interaction-specific and evidence details.
-- **Status:** FIXED (combined with Gap 5)
-- **Fix:** Add fields to `RoleLessonEntry`.
-
-### Gap 22: `TeamLessonEntry` simplified vs design
-- **Source:** DESIGN has `compositionLessons` and `coordinationLessons` with structured categories (`'role-necessity' | 'team-size' | 'topology' | 'model-selection'` and `'delegation' | 'communication' | 'synchronization' | 'escalation'`).
-- **Impact:** Less structured lesson categorization.
-- **Status:** FIXED
-- **Fix:** Add specific subcategory types.
-
-### Gap 23: Deduplication threshold not wired from config
-- **Source:** Config has `deduplicationThreshold: 0.85` but heuristic extraction uses hardcoded `0.85`.
-- **Impact:** Config value is ignored.
-- **Status:** FIXED
-- **Fix:** Pass config value through to extraction.
-
-### Gap 24: `TeamMetaObservation` shape diverges from DESIGN
-- **Source:** PROPOSAL version (implemented) has `formation.confidence/reasoning`. DESIGN version has `formation.wasEffective`. Implementation lacks `lessons.roleSuggestions`.
-- **Impact:** Minor type mismatch.
-- **Status:** FIXED
-- **Fix:** Add `wasEffective` field to `FormationObservation` and `roleSuggestions` to `TeamLessonsLearned`.
-
-### Gap 25: Missing analysis domain tag
-- **Source:** DESIGN specifies analysis agent trajectory should be tagged with domain `"team-analysis"` for recursive learning.
-- **Impact:** If analysis agent trajectories are ever captured, they won't be domain-tagged.
-- **Status:** DEFERRED - Depends on Gap 8 (analysis agent meta-learning loop).
-- **Fix:** N/A
-
-### Gap 26: `CoordinationAssessment` missing `patternComparison`
-- **Source:** DESIGN specifies `patternComparison: { expected, observed, impact }[]`.
-- **Impact:** No structured comparison of expected vs actual coordination patterns.
-- **Status:** FIXED (combined with Gap 5)
-- **Fix:** Add field.
-
-### Gap 27: `CoordinationAssessment` missing `emergentCoordination`
-- **Source:** DESIGN specifies `emergentCoordination: { description, wasHelpful, shouldBeFormalized }[]`.
-- **Impact:** No tracking of emergent coordination patterns.
-- **Status:** FIXED (combined with Gap 5)
-- **Fix:** Add field.
-
-### Gap 28: `RoleInteractionGuidance.interactionType` uses `string`
-- **Source:** Should use `InteractionType` union from DESIGN.
-- **Impact:** No type safety on interaction types.
-- **Status:** FIXED (combined with Gap 16)
-- **Fix:** Update type to use `InteractionType`.
-
-### Gap 29: No `TeamBatchResult.ready` field
-- **Source:** DESIGN specifies `TeamBatchResult.ready: boolean` to indicate whether batch was actually run.
-- **Impact:** Caller can't distinguish "batch ran and produced nothing" from "batch not ready".
-- **Status:** FIXED
-- **Fix:** Add `ready` field.
-
-### Gap 30: `TeamProcessResult` type mismatch between Atlas and Pipeline
-- **Source:** Atlas defines its own `TeamProcessResult` (`{ teamTrajectoryId, stored }`) different from pipeline's (`{ teamTrajectoryId, stored, analyzed, analysis? }`).
-- **Impact:** Atlas method returns less information than pipeline produces.
-- **Status:** FIXED
-- **Fix:** Unify types; Atlas should re-export pipeline's type or extend it.

package/scripts/migrate-to-playbooks.ts

@@ -1,307 +0,0 @@
-#!/usr/bin/env npx tsx
-/**
- * Migration Script: Strategy + Skill → Playbook
- *
- * Converts existing Strategy and Skill data to the new Playbook format.
- * Run this script to migrate your data after updating to the new architecture.
- *
- * Usage:
- *   npx tsx scripts/migrate-to-playbooks.ts [--data-dir=.atlas] [--dry-run]
- */
-
-import { readFileSync, writeFileSync, existsSync, mkdirSync } from 'node:fs';
-import { join } from 'node:path';
-import type { Strategy, Skill, Playbook } from '../src/types/index.js';
-import { createPlaybook } from '../src/types/index.js';
-import { textSimilarity } from '../src/utils/similarity.js';
-
-// Parse command line arguments
-const args = process.argv.slice(2);
-const dryRun = args.includes('--dry-run');
-const dataDirArg = args.find((a) => a.startsWith('--data-dir='));
-const dataDir = dataDirArg ? dataDirArg.split('=')[1] : '.atlas';
-
-console.log('=== Playbook Migration Script ===\n');
-console.log(`Data directory: ${dataDir}`);
-console.log(`Dry run: ${dryRun}\n`);
-
-/**
- * Load JSON data from a file
- */
-function loadJsonData<T>(filePath: string): T | null {
-  if (!existsSync(filePath)) {
-    console.log(`  File not found: ${filePath}`);
-    return null;
-  }
-
-  try {
-    const content = readFileSync(filePath, 'utf-8');
-    return JSON.parse(content) as T;
-  } catch (error) {
-    console.error(`  Error reading ${filePath}:`, error);
-    return null;
-  }
-}
-
-/**
- * Save JSON data to a file
- */
-function saveJsonData(filePath: string, data: unknown): void {
-  if (dryRun) {
-    console.log(`  [DRY RUN] Would write to: ${filePath}`);
-    return;
-  }
-
-  const dir = filePath.substring(0, filePath.lastIndexOf('/'));
-  if (!existsSync(dir)) {
-    mkdirSync(dir, { recursive: true });
-  }
-
-  writeFileSync(filePath, JSON.stringify(data, null, 2));
-  console.log(`  Written: ${filePath}`);
-}
-
-/**
- * Generate a kebab-case playbook name
- */
-function generatePlaybookName(text: string): string {
-  return text
-    .toLowerCase()
-    .replace(/[^\w\s]/g, '')
-    .split(/\s+/)
-    .filter((w) => w.length > 2)
-    .slice(0, 4)
-    .join('-') || `playbook-${Date.now()}`;
-}
-
-/**
- * Convert a Skill to a Playbook
- */
-function skillToPlaybook(skill: Skill): Playbook {
-  return createPlaybook({
-    id: `playbook-skill-${skill.id}`,
-    name: skill.name,
-    applicability: {
-      situations: [skill.description],
-      triggers: skill.triggers || [],
-      antiPatterns: [],
-      domains: skill.domain ? [skill.domain] : [],
-    },
-    guidance: {
-      strategy: skill.description,
-      tactics: skill.solution || [],
-      steps: skill.solution || [],
-    },
-    verification: {
-      successIndicators: skill.verification ? [skill.verification] : [],
-      failureIndicators: [],
-    },
-    evolution: {
-      version: skill.version || '1.0.0',
-      createdFrom: [],
-      failures: [],
-      refinements: [],
-      successCount: Math.round((skill.usageCount || 0) * (skill.successRate || 0.5)),
-      failureCount: Math.round((skill.usageCount || 0) * (1 - (skill.successRate || 0.5))),
-    },
-    confidence: skill.successRate || 0.5,
-    complexity: (skill.solution?.length || 0) > 5 ? 'complex' : 'moderate',
-    estimatedEffort: skill.solution?.length || 3,
-    createdAt: skill.createdAt ? new Date(skill.createdAt) : new Date(),
-    updatedAt: skill.updatedAt ? new Date(skill.updatedAt) : new Date(),
-  });
-}
-
-/**
- * Convert a Strategy to a Playbook
- */
-function strategyToPlaybook(strategy: Strategy): Playbook {
-  return createPlaybook({
-    id: `playbook-strategy-${strategy.id}`,
-    name: generatePlaybookName(strategy.situation),
-    applicability: {
-      situations: [strategy.situation],
-      triggers: [], // Strategies are more abstract, fewer triggers
-      antiPatterns: [],
-      domains: strategy.domain ? [strategy.domain] : [],
-    },
-    guidance: {
-      strategy: strategy.suggestion,
-      tactics: (strategy.parameters as Record<string, unknown>)?.steps as string[] || [],
-    },
-    verification: {
-      successIndicators: [],
-      failureIndicators: [],
-    },
-    evolution: {
-      version: '1.0.0',
-      createdFrom: strategy.sourceTrajectoryIds || [],
-      failures: [],
-      refinements: [],
-      successCount: Math.round((strategy.usageCount || 0) * (strategy.successRate || 0.5)),
-      failureCount: Math.round((strategy.usageCount || 0) * (1 - (strategy.successRate || 0.5))),
-    },
-    confidence: strategy.confidence || 0.5,
-    complexity: 'moderate',
-    estimatedEffort: 3,
-    createdAt: strategy.createdAt ? new Date(strategy.createdAt) : new Date(),
-    updatedAt: strategy.updatedAt ? new Date(strategy.updatedAt) : new Date(),
-  });
-}
-
-/**
- * Merge similar playbooks
- */
-function mergePlaybooks(playbooks: Playbook[]): Playbook[] {
-  const merged: Playbook[] = [];
-  const used = new Set<string>();
-
-  for (const playbook of playbooks) {
-    if (used.has(playbook.id)) continue;
-
-    // Find similar playbooks
-    let current = playbook;
-    for (const other of playbooks) {
-      if (used.has(other.id) || other.id === current.id) continue;
-
-      // Check similarity
-      const situationSimilarity = Math.max(
-        ...current.applicability.situations.flatMap((s1) =>
-          other.applicability.situations.map((s2) => textSimilarity(s1, s2))
-        ),
-        0
-      );
-
-      if (situationSimilarity > 0.85) {
-        // Merge
-        console.log(`  Merging: ${other.name} into ${current.name}`);
-        current = {
-          ...current,
-          applicability: {
-            ...current.applicability,
-            situations: [...new Set([...current.applicability.situations, ...other.applicability.situations])],
-            triggers: [...new Set([...current.applicability.triggers, ...other.applicability.triggers])],
-            domains: [...new Set([...current.applicability.domains, ...other.applicability.domains])],
-          },
-          guidance: {
-            ...current.guidance,
-            tactics: [...new Set([...current.guidance.tactics, ...other.guidance.tactics])],
-          },
-          evolution: {
-            ...current.evolution,
-            createdFrom: [...new Set([...current.evolution.createdFrom, ...other.evolution.createdFrom])],
-            successCount: current.evolution.successCount + other.evolution.successCount,
-            failureCount: current.evolution.failureCount + other.evolution.failureCount,
-          },
-          confidence: Math.max(current.confidence, other.confidence),
-        };
-        used.add(other.id);
-      }
-    }
-
-    merged.push(current);
-    used.add(current.id);
-  }
-
-  return merged;
-}
-
-/**
- * Main migration function
- */
-async function migrate(): Promise<void> {
-  console.log('Step 1: Loading existing data...\n');
-
-  // Load strategies
-  const strategiesPath = join(dataDir, 'strategies.json');
-  const strategiesData = loadJsonData<Record<string, Strategy>>(strategiesPath);
-  const strategies = strategiesData ? Object.values(strategiesData) : [];
-  console.log(`  Found ${strategies.length} strategies`);
-
-  // Load skills
-  const skillsPath = join(dataDir, 'skills.json');
-  const skillsData = loadJsonData<Record<string, Skill>>(skillsPath);
-  const skills = skillsData ? Object.values(skillsData) : [];
-  console.log(`  Found ${skills.length} skills`);
-
-  if (strategies.length === 0 && skills.length === 0) {
-    console.log('\nNo data to migrate. Exiting.');
-    return;
-  }
-
-  console.log('\nStep 2: Converting to playbooks...\n');
-
-  // Convert skills first (they're more concrete)
-  const fromSkills = skills.map(skillToPlaybook);
-  console.log(`  Converted ${fromSkills.length} skills to playbooks`);
-
-  // Convert strategies
-  const fromStrategies = strategies.map(strategyToPlaybook);
-  console.log(`  Converted ${fromStrategies.length} strategies to playbooks`);
-
-  // Combine
-  const allPlaybooks = [...fromSkills, ...fromStrategies];
-
-  console.log('\nStep 3: Merging similar playbooks...\n');
-  const mergedPlaybooks = mergePlaybooks(allPlaybooks);
-  console.log(`  Merged to ${mergedPlaybooks.length} unique playbooks`);
-
-  console.log('\nStep 4: Saving playbooks...\n');
-
-  // Create playbooks record
-  const playbooksRecord: Record<string, Playbook> = {};
-  for (const playbook of mergedPlaybooks) {
-    playbooksRecord[playbook.id] = playbook;
-  }
-
-  // Save playbooks
-  const playbooksPath = join(dataDir, 'playbooks.json');
-  saveJsonData(playbooksPath, playbooksRecord);
-
-  console.log('\nStep 5: Creating migration report...\n');
-
-  const report = {
-    timestamp: new Date().toISOString(),
-    dryRun,
-    source: {
-      strategiesCount: strategies.length,
-      skillsCount: skills.length,
-    },
-    result: {
-      playbooksCount: mergedPlaybooks.length,
-      mergedCount: allPlaybooks.length - mergedPlaybooks.length,
-    },
-    playbooks: mergedPlaybooks.map((p) => ({
-      id: p.id,
-      name: p.name,
-      domains: p.applicability.domains,
-      confidence: p.confidence,
-      successCount: p.evolution.successCount,
-    })),
-  };
-
-  const reportPath = join(dataDir, 'migration-report.json');
-  saveJsonData(reportPath, report);
-
-  console.log('\n=== Migration Complete ===\n');
-  console.log('Summary:');
-  console.log(`  - Strategies migrated: ${strategies.length}`);
-  console.log(`  - Skills migrated: ${skills.length}`);
-  console.log(`  - Playbooks created: ${mergedPlaybooks.length}`);
-  console.log(`  - Playbooks merged: ${allPlaybooks.length - mergedPlaybooks.length}`);
-
-  if (dryRun) {
-    console.log('\n[DRY RUN] No files were modified. Run without --dry-run to apply changes.');
-  } else {
-    console.log('\nPlaybooks saved to:', playbooksPath);
-    console.log('Migration report saved to:', reportPath);
-    console.log('\nNote: Original strategy and skill files were not modified.');
-    console.log('You can delete them after verifying the migration.');
-  }
-}
-
-// Run migration
-migrate().catch((error) => {
-  console.error('Migration failed:', error);
-  process.exit(1);
-});

package/src/agents/index.ts

@@ -1,14 +0,0 @@
-// Types and base classes
-export {
-  Agent,
-  type LLMProvider,
-  type Message,
-  type CompletionOptions,
-  type AgentConfig,
-  type ToolDefinition,
-  type ToolCall,
-  type ToolAgent,
-} from './types.js';
-
-// Mock provider for testing
-export { MockLLMProvider, createMockProvider } from './mock-provider.js';

package/src/agents/mock-provider.ts

@@ -1,93 +0,0 @@
-import type { LLMProvider, Message, CompletionOptions } from './types.js';
-
-/**
- * Mock LLM provider for testing
- * Returns predefined responses based on input patterns
- */
-export class MockLLMProvider implements LLMProvider {
-  readonly name = 'mock';
-
-  private responses: Map<RegExp, string> = new Map();
-
-  constructor() {
-    // Default mock responses
-    this.addResponse(
-      /extract.*strateg/i,
-      `STRATEGY:
-- Situation: When facing a debugging task with unclear error messages
-- Suggestion: Start by reproducing the issue, then use binary search to isolate the problem
-- Parameters: error_message, codebase_size
-- Confidence: 0.7`
-    );
-
-    this.addResponse(
-      /extract.*concept/i,
-      `CONCEPT:
-- Name: error-handler
-- Description: Generic error handling wrapper function
-- Code: \`\`\`typescript
-function handleError<T>(fn: () => T): T | null {
-  try {
-    return fn();
-  } catch (e) {
-    console.error(e);
-    return null;
-  }
-}
-\`\`\`
-- Signature: (() => T) -> T | null`
-    );
-
-    this.addResponse(
-      /extract.*skill|codify.*skill/i,
-      `SKILL:
-- Name: fix-typescript-import-error
-- Problem: Resolve TypeScript module import errors
-- Triggers: Cannot find module, Module not found, TS2307
-- Steps:
-  1. Check if the module is installed in package.json
-  2. Verify the import path is correct
-  3. Check tsconfig.json module resolution settings
-  4. Run npm install or yarn if module is missing
-- Verification: Run tsc --noEmit to verify no import errors`
-    );
-  }
-
-  /**
-   * Add a custom response pattern
-   */
-  addResponse(pattern: RegExp, response: string): void {
-    this.responses.set(pattern, response);
-  }
-
-  /**
-   * Generate a completion (mock)
-   */
-  async complete(
-    messages: Message[],
-    _options?: CompletionOptions
-  ): Promise<string> {
-    // Get the last user message
-    const lastMessage = messages.filter((m) => m.role === 'user').pop();
-    if (!lastMessage) {
-      return 'No user message found.';
-    }
-
-    // Check patterns
-    for (const [pattern, response] of this.responses) {
-      if (pattern.test(lastMessage.content)) {
-        return response;
-      }
-    }
-
-    // Default response
-    return 'No matching pattern found for this request.';
-  }
-}
-
-/**
- * Create a mock provider for testing
- */
-export function createMockProvider(): MockLLMProvider {
-  return new MockLLMProvider();
-}